Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code snippets related to programming logic and template syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming code and files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jspb
    -0.39
    原始内容存档于
    -0.39
    iería
    -0.38
    ukses
    -0.37
    pausal
    -0.36
    intios
    -0.35
     المعيارى
    -0.35
     sukienka
    -0.35
     agente
    -0.34
     posando
    -0.34
    POSITIVE LOGITS
    IntoConstraints
    0.57
    发表于
    0.45
    MLLoader
    0.45
    styleable
    0.43
     ujednoznacz
    0.43
     toppen
    0.42
    BibitemShut
    0.42
     kasarigan
    0.42
     Mist
    0.42
    ="@+
    0.42
    Act Density 0.076%

    No Known Activations